Show simple item record

dc.contributor.authorOzgur, Cemile
dc.contributor.authorSarikovanlik, Vedat
dc.date.accessioned2023-02-21T09:28:49Z
dc.date.available2023-02-21T09:28:49Z
dc.date.issued2022
dc.identifier.citationOzgur C., Sarikovanlik V., "FORECASTING BIST100 AND NASDAQ INDICES WITH SINGLE AND HYBRID MACHINE LEARNING ALGORITHMS", ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, cilt.56, sa.3, ss.235-250, 2022
dc.identifier.issn0424-267X
dc.identifier.othervv_1032021
dc.identifier.otherav_2ee71640-33ed-443c-b532-318c405621db
dc.identifier.urihttp://hdl.handle.net/20.500.12627/187517
dc.identifier.urihttps://avesis.istanbul.edu.tr/api/publication/2ee71640-33ed-443c-b532-318c405621db/file
dc.identifier.urihttps://doi.org/10.24818/18423264/56.3.22.15
dc.description.abstractThe aim of this paper is to investigate stock market return forecasting performance of single and the developed novel hybrid machine learning (ML) algorithms. Daily returns of BIST100 and NASDAQ indices are predicted by series specific GARCH and ARMA-GARCH as well as three different ML algorithms that are Random Forest, XGBoost and Artificial Neural Networks (ANN). New hybrid ML models incorporating forecasts of the traditional (ARMA-)GARCH and the three ML algorithms are developed. Accuracy of the out-of-sample predictions of the methods are reported both for the single and hybrid models including pre-COVID-19, post-COVID-19 and the full sample test periods. Moreover, a simple trading strategy is applied in order to assess the economic impact of employing a specific forecasting model. According to the obtained accuracy metrics and the results of the trading strategy, developed novel hybrid models suggest quite promising results compared to the forecasts of the other models, especially (ARMA)GARCH.
dc.language.isoeng
dc.subjectAnaliz
dc.subjectCebir ve Sayı Teorisi
dc.subjectMatematik (çeşitli)
dc.subjectSosyal Bilimler (SOC)
dc.subjectEkonomi ve İş
dc.subjectGenel Matematik
dc.subjectEkonomi ve Ekonometri
dc.subjectEkonomi, Ekonometri ve Finans (çeşitli)
dc.subjectGenel Ekonomi, Ekonometri ve Finans
dc.subjectFizik Bilimleri
dc.subjectSosyal Bilimler ve Beşeri Bilimler
dc.subjectEKONOMİ
dc.subjectHesaplamalı Matematik
dc.subjectİktisat
dc.subjectSosyal ve Beşeri Bilimler
dc.subjectTemel Bilimler (SCI)
dc.subjectMatematik
dc.subjectMATEMATİK, DİSİPLİNLERARASI UYGULAMALAR
dc.titleFORECASTING BIST100 AND NASDAQ INDICES WITH SINGLE AND HYBRID MACHINE LEARNING ALGORITHMS
dc.typeMakale
dc.relation.journalECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH
dc.contributor.departmentİstanbul Üniversitesi , İşletme Fakültesi , İşletme Bölümü
dc.identifier.volume56
dc.identifier.issue3
dc.identifier.startpage235
dc.identifier.endpage250
dc.contributor.firstauthorID4144702


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record